AImodelsComparison.com 1,213 open · 210 API
Menu
Models Best of Trending Can I run it? Methodology MCP server About
1,213 models · 1,213 open weights · 210 API-only · refreshed nightly

Open-weights models

Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.

Type
All 1,423 Open weights (self-host) 1,213 API-only 210
Task
All text-generation 539 text-to-image 155 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 token-classification 22 text-to-speech 19 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 audio-text-to-text 1 any-to-any 1
Runs on
Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB
Licence
Size
$
654 models
#ModelParamsContextCommercial use30dOn RTX 4070 · 16 GB
301 deberta-v3-base-prompt-injection-v2 protectai · text-classification Open weights 180 M 512 ✓ apache-2.0 521 K 1.3 GB
302 japanese-gpt-neox-small rinna · text-generation Open weights 200 M 2 K ✓ mit 520 K 1.3 GB
303 snowflake-arctic-embed-l Snowflake · sentence-similarity Open weights 334 M 512 ✓ apache-2.0 519 K 2.0 GB
304 Qwen3-VL-Embedding-2B Qwen · sentence-similarity Open weights 2.1 B — ✓ apache-2.0 517 K 5.5 GB
305 jina-embeddings-v5-text-nano jinaai · feature-extraction Open weights 210 M 8 K ✗ cc-by-nc-4.0 515 K 1.1 GB
306 langcache-embed-v1 redis · sentence-similarity Open weights 149 M 8 K unknown 514 K 1.2 GB
307 Pruna-Qage-2.1 PrunaAI · text-to-image Open weights 7.1 B — other 514 K 2.3 GB
308 Pruna-Qwen-Image-2.1 PrunaAI · text-to-image Open weights 7.1 B — other 513 K 2.3 GB
309 Qwen3.8-2B-Distill-GGUF empero-ai · text-generation Open weights — — ✓ apache-2.0 510 K 1.9 GB
310 Pruna-Q-Image-2.1 PrunaAI · text-to-image Open weights 7.1 B — other 510 K 2.3 GB
311 deepset-mxbai-embed-de-large-v1 mixedbread-ai · feature-extraction Open weights 487 M 512 ✓ apache-2.0 504 K 1.6 GB
312 POCKET-35B-GGUF FINAL-Bench · text-generation Open weights 35.0 B — ✓ apache-2.0 504 K 14.8 GB
313 snowflake-arctic-embed-s Snowflake · sentence-similarity Open weights 30 M 512 ✓ apache-2.0 496 K 0.7 GB
314 Qwen2.5-1.5B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 494 K 1.3 GB
315 Sage-A1.5-Q8_0-GGUF InternScience · text-generation Open weights — — ✓ apache-2.0 490 K 1.5 GB
316 Qwen3-Coder-30B-A3B-Instruct-GGUF unsloth · text-generation Open weights — — ✓ apache-2.0 486 K 12.9 GB
317 Voxtral-Mini-4B-Realtime-2602-gguf handy-computer · ASR Open weights 4.0 B — ✓ apache-2.0 485 K 4.2 GB
318 stable-diffusion-v1-4 CompVis · text-to-image Open weights 860 M — ⚠ creativeml-openrail-m 483 K 13.5 GB
319 Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 482 K 7.8 GB
320 Qwen3.8-27B-DFlash2-GGUF z-lab · text-generation Open weights — — ✓ apache-2.0 481 K 1.8 GB
321 NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF unsloth · text-generation Open weights 4.0 B — other 481 K 5.0 GB
322 Llama-3.2-1B meta-llama · text-generation · gated Open weights 1.2 B — ⚠ llama3.2 477 K 3.4 GB
323 embeddinggemma-2 google · feature-extraction Open weights 744 M — ✓ apache-2.0 475 K 2.2 GB
324 sentence-bert-base-ja-mean-tokens-v2 sonoisa · feature-extraction Open weights 110 M 512 cc-by-sa-4.0 474 K 1.0 GB
325 llama-3-8b-Instruct-bnb-4bit unsloth · text-generation Open weights 8.2 B 8 K ⚠ llama3 472 K 8.0 GB
326 wav2vec2-large-xlsr-japanese-hiragana vumichien · ASR Open weights 320 M — ✓ apache-2.0 472 K 1.9 GB
327 nli-mpnet-base-v2 sentence-transformers · sentence-similarity Open weights 110 M 512 ✓ apache-2.0 472 K 1.0 GB
328 bge-small-en-v1.5 unsloth · feature-extraction Open weights 33 M 512 ✓ mit 470 K 0.7 GB
329 wav2vec2-large-xlsr-kazakh aismlv · ASR Open weights 320 M — ✓ apache-2.0 466 K 1.9 GB
330 pplx-embed-v1-0.6b perplexity-ai · feature-extraction Open weights 600 M 33 K ✓ mit 461 K 3.2 GB
331 rubert-tiny2 cointegrated · sentence-similarity Open weights 30 M 2 K ✓ mit 460 K 0.6 GB
332 nsfw_image_detector Freepik · image-classification Open weights 90 M — ✓ mit 460 K 0.7 GB
333 sat-3l-sm segment-any-text · token-classification Open weights 210 M 514 ✓ mit 460 K 1.5 GB
334 robertuito-sentiment-analysis pysentimiento · text-classification Open weights 110 M 128 unknown 459 K 1.0 GB
335 gpt-neo-125m EleutherAI · text-generation Open weights 150 M 2 K ✓ mit 458 K 1.1 GB
336 mimi kyutai · feature-extraction Open weights 100 M 8 K ✓ cc-by-4.0 458 K 0.9 GB
337 multilingual-e5-small Xenova · feature-extraction Open weights 120 M 512 unknown 456 K 0.8 GB
338 MedCPT-Query-Encoder ncbi · feature-extraction Open weights 110 M 512 other 454 K 1.0 GB
339 sd-turbo stabilityai · text-to-image Open weights 870 M — unknown 454 K 14.9 GB
340 open-vakgyata onecxi · audio-classification Open weights 60 M — ✗ cc-by-nc-4.0 453 K 0.8 GB
341 gte-base-en-v1.5 Alibaba-NLP · sentence-similarity Open weights 137 M 8 K ✓ apache-2.0 452 K 1.1 GB
342 Qwen3-4B-Base Qwen · text-generation Open weights 4.0 B 33 K ✓ apache-2.0 447 K 10.0 GB
343 Mellum2.1-12B-A2.5B-Thinking-GGUF JetBrains · text-generation Open weights 12.0 B — ✓ apache-2.0 446 K 11.5 GB
344 MiniCPM5-2B-GGUF openbmb · text-generation Open weights 2.0 B — ✓ apache-2.0 446 K 2.5 GB
345 Qwen2.5-Coder-3B-Instruct Qwen · text-generation Open weights 3.1 B 33 K other 441 K 7.8 GB
346 sqlcoder-7b-2 defog · text-generation Open weights 6.7 B 16 K cc-by-sa-4.0 441 K 6.8 GB
347 nllb-200-distilled-1.3B facebook · translation Open weights 1.3 B 1 K ✗ cc-by-nc-4.0 440 K 3.6 GB
348 Qwen2.5-0.5B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 440 K 1.0 GB
349 Apodex-1.1-mini-GGUF abenzerps · text-generation Open weights — — ✓ apache-2.0 439 K 10.2 GB
350 S-PubMedBert-MedQuAD TimKond · sentence-similarity Open weights 110 M 512 ✓ mit 439 K 1.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.